一种基于MGWO-Informer的超短期风电功率预测方法

王颉; 刘兴杰; 梁英; 薄天利

doi:10.19912/j.0254-0096.tynxb.2023-1192

PDF(1943 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (11) : 477-485. DOI: 10.19912/j.0254-0096.tynxb.2023-1192

一种基于MGWO-Informer的超短期风电功率预测方法

王颉, 刘兴杰, 梁英, 薄天利

作者信息 +

AN ULTRA-SHORT-TERM WIND POWER PREDICTION METHOD BASED ON MGWO-INFORMER

Wang Jie, Liu Xingjie, Liang Ying, Bo Tianli

Author information +

文章历史 +

摘要

针对Informer在风电功率预测存在超参数寻优不准确、预测精度较低等问题,提出一种基于MGWO-Informer的超短期风电功率预测模型。首先,为解决传统灰狼进化算法在一些寻优过程中存在求解精度不高、易陷入局部最优的缺点,提出一种增强全局搜索的改进灰狼优化算法（MGWO）,该算法提出新收敛因子策略和阶段性位置更新策略两种改进策略。其次,利用改进后的灰狼算法对Informer模型参数进行寻优,以提高模型超参数寻优的准确性。最后,以中国西北地区某风电场实测数据为例,将预测结果同门控循环神经网络（GRU）、长短时记忆神经网络（LSTM）和Transformer进行对比实验。结果表明,改进后的Informer模型具有较高的预测精度和运行效率,平均绝对误差（eMAE）和均方根误差（eRMSE）分别下降了26.74%和19.74%,拟合系数（R2）提升了1.41%。

Abstract

Aiming at the problems of inaccurate hyper-parameter optimization and low prediction accuracy of Informer in wind power prediction, an ultra-short-term wind power prediction model based on MGWO-Informer is proposed. Firstly, in order to solve the shortcomings of the traditional Grey Wolf evolutionary algorithm, which has the disadvantages of poor solution accuracy and easy to fall into the local optimum in some of the optimization searching processes, a Modified Grey Wolf Optimizer （MGWO） algorithm is proposed to enhance the global searching, which proposes 2 kinds of improvement strategies： the new convergence factor and the staged position updating. Second, the Informer model parameters are optimized using the improved Gray Wolf algorithm to improve the accuracy of model hyperparameter optimization. Finally, taking the measured data of a wind farm in Northwest China as an example, the prediction results are compared with gate recurrent unit （GRU）, long short term memory （LSTM） and transformer. The results indicate that the improved Informer model has high prediction accuracy and operational efficiency, with a decrease of 26.74% in mean absolute error and 19.74% in root mean square error, and an increase of 1.41% in fitting coefficient.

导出引用

王颉, 刘兴杰, 梁英, 薄天利. 一种基于MGWO-Informer的超短期风电功率预测方法[J]. 太阳能学报. 2024, 45(11): 477-485 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1192

Wang Jie, Liu Xingjie, Liang Ying, Bo Tianli. AN ULTRA-SHORT-TERM WIND POWER PREDICTION METHOD BASED ON MGWO-INFORMER[J]. Acta Energiae Solaris Sinica. 2024, 45(11): 477-485 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1192

中图分类号： TM614

参考文献

[1] 朱蓉, 王阳, 向洋, 等. 中国风能资源气候特征和开发潜力研究[J]. 太阳能学报, 2021, 42(6): 409-418.
ZHU R, WANG Y, XIANG Y, et al.Study on climatic characteristics and development potential of wind energy resources in China[J]. Acta energiae solaris sinica, 2021, 42(6): 409-418.
[2] 吕萍, 石耀鹏. 中国风电产业进入市场化高质量发展阶段[J]. 风能, 2023(5): 72-76.
LYU P, SHI Y P.China wind power industry has entered the stage of market-oriented and high-quality development[J]. Wind energy, 2023(5): 72-76.
[3] 杨国清, 刘世林, 王德意, 等. 基于Attention-GRU风速修正和Stacking的短期风电功率预测[J]. 太阳能学报, 2022, 43(12): 273-281.
YANG G Q, LIU S L, WANG D Y, et al.Short-term wind power forecasting based on Attention-GRU wind speed correction and stacking[J]. Acta energiae solaris sinica, 2022, 43(12): 273-281.
[4] 黄鹏翔, 周云海, 徐飞, 等. 基于负荷与风电出力场景集的运行备用动态调度方法[J]. 可再生能源, 2021, 39(5): 658-665.
HUANG P X, ZHOU Y H, XU F, et al.Dynamic scheduling method for operational reserve based on load and wind power output scenario set[J]. Renewable energy resources, 2021, 39(5): 658-665.
[5] 杨茂, 张罗宾. 基于数据驱动的超短期风电功率预测综述[J]. 电力系统保护与控制, 2019, 47(13): 171-186.
YANG M, ZHANG L B.Review on ultra-short term wind power forecasting based on data-driven approach[J]. Power system protection and control, 2019, 47(13): 171-186.
[6] 张尧翔, 刘文颖, 庞清仑, 等. 高比例风电接入系统光热发电-火电旋转备用优化方法[J]. 电工技术学报, 2022, 37(21): 5478-5489.
ZHANG Y X, LIU W Y, PANG Q L, et al.Optimal power spinning reserve method of concentrating solar power and thermal power for high-proportion wind power system[J]. Transactions of China Electrotechnical Society, 2022, 37(21): 5478-5489.
[7] 杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J].计算机应用, 2018, 38(增刊2): 1-6,26.
YANG L, WU Y Q, WANG J L, et al.Review of recurrent neural network[J]. Journal of computer applications, 2018, 38(Sup 2): 1-6,26.
[8] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[EB/OL]. http://arxiv.org/abs/1706.03762.
[9] ZHOU H Y, ZHANG S H, PENG J Q, et al.Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(12): 11106-11115.
[10] WEI H, WANG W S, KAO X X.A novel approach to ultra-short-term wind power prediction based on feature engineering and informer[J]. Energy reports, 2023, 9: 1236-1250.
[11] 孙晗喆, 陈洁, 梁帅, 等. 基于改进黏菌算法的风光电并网双层储能容量优化[J]. 电网与清洁能源, 2023, 39(5): 128-136.
SUN H Z, CHEN J, LIANG S, et al.Optimization of double-layer energy storage capacity of photovoltaic grid-connected system based on improved slime mold algorithm[J]. Power system and clean energy, 2023, 39(5): 128-136.
[12] 蒲娴怡, 毕贵红, 王凯, 等. 基于二层分解的PSO-LSTM模型风电功率超短期预测[J]. 电机与控制应用, 2021, 48(5): 86-92.
PU X Y, BI G H, WANG K, et al.Ultra-short-term wind power prediction based on two-layer decomposition technique and PSO-LSTM model[J]. Electric machines & control application, 2021, 48(5): 86-92.
[13] 高超, 孙谊媊, 赵洪峰, 等. 基于ICEEMDAN-ISSA-LSTM的短期电力负荷预测[J]. 中国测试, 2023(9): 99-107.
GAO C, SUN Y Q, ZHAO H F, et al.Short-term power load forecasting based on ICEEMDAN-ISSA-LSTM[J]. China test, 2023(9): 99-107.
[14] 王瑞, 徐新超, 逯静. 基于特征选择及ISSA-CNN-BiGRU的短期风功率预测[J]. 工程科学与技术, 2024(3): 228-239.
WANG R, XU X C, LU J.Short-term wind power prediction based on feature selection and ISSA-CNN-BiGRU[J]. Advanced engineering sciences, 2024(3): 228-239.
[15] 王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.
WANG W G, WEI Y B, TENG X D.Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta energiae solaris sinica, 2023, 44(3): 204-211.
[16] 张阳, 周溪召. 求解全局优化问题的改进灰狼算法[J]. 上海理工大学学报, 2021, 43(1): 73-82.
ZHANG Y, ZHOU X Z.Modified grey wolf optimization algorithm for global optimization problems[J]. Journal of University of Shanghai for Science and Technology, 2021, 43(1): 73-82.
[17] MIRJALILI S, MIRJALILI S M, LEWIS A.Grey wolf optimizer[J]. Advances in engineering software, 2014, 69: 46-61.
[18] 赵超, 王斌, 孙志新, 等. 基于改进灰狼算法的独立微电网容量优化配置[J]. 太阳能学报, 2022, 43(1): 256-262.
ZHAO C, WANG B, SUN Z X, et al.Optimal configuration optimization of islanded microgrid using improved grey wolf optimizer algorithm[J]. Acta energiae solaris sinica, 2022, 43(1): 256-262.
[19] 郭振洲, 刘然, 拱长青, 等. 基于灰狼算法的改进研究[J]. 计算机应用研究, 2017, 34(12): 3603-3606, 3610.
GUO Z Z, LIU R, GONG C Q, et al.Study on improvement of gray wolf algorithm[J]. Application research of computers, 2017, 34(12): 3603-3606, 3610.
[20] 余帆, 王磊, 江巧永, 等. 基于特征筛选的VMD-MIC-SSA-Informer短期负荷预测[J]. 陕西科技大学学报, 2022, 40(5): 191-196, 203.
YU F, WANG L, JIANG Q Y, et al.VMD-MIC-SSA-Informer short-term load prediction based on feature selection[J]. Journal of Shaanxi University of Science & Technology, 2022, 40(5): 191-196, 203.
[21] 滕陈源, 丁逸超, 张有兵, 等. 基于VMD-Informer-BiLSTM模型的超短期光伏功率预测[J].高电压技术, 2023(7): 2961-2971.
TENG C Y, DING Y C, ZHANG Y B, et al.Ultra short term photovoltaic power prediction based on VMD-Informer BiLSTM model[J]. High voltage engineering, 2023(7): 2961-2971.
[22] 张晓凤, 王秀英. 灰狼优化算法研究综述[J]. 计算机科学, 2019, 46(3): 30-38.
ZHANG X F, WANG X Y.Comprehensive review of grey wolf optimization algorithm[J]. Computer science, 2019, 46(3): 30-38.
[23] 李雅丽, 王淑琴, 陈倩茹, 等. 若干新型群智能优化算法的对比研究[J]. 计算机工程与应用, 2020, 56(22): 1-12.
LI Y L, WANG S Q, CHEN Q R, et al.Comparative study of several new swarm intelligence optimization algorithms[J]. Computer engineering and applications, 2020, 56(22): 1-12.
[24] NB/T 31046—2013, 风电功率预测系统功能规范[S].
NB/T 31046—2013, Function specification of wind power forecasting system[S].